CN108563990B - Certificate authentication method and system based on CIS image acquisition system - Google Patents
Certificate authentication method and system based on CIS image acquisition system Download PDFInfo
- Publication number
- CN108563990B CN108563990B CN201810190966.4A CN201810190966A CN108563990B CN 108563990 B CN108563990 B CN 108563990B CN 201810190966 A CN201810190966 A CN 201810190966A CN 108563990 B CN108563990 B CN 108563990B
- Authority
- CN
- China
- Prior art keywords
- image
- license
- infrared
- images
- certificate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Credit Cards Or The Like (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a certificate authentication method and system based on a CIS image acquisition system, wherein the method comprises the steps of correcting an acquired certificate image, detecting and dividing a certificate image identification area, identifying surface characters of the certificate image, reading information of a certificate chip and authenticating the certificate image; the system comprises a transmission device, a CIS tube image acquisition system, a main control module, an identity card or passport chip reading module, an upper computer interface and a computer program which is stored in the upper computer and executes the steps of the certificate authentication method when being called; the certificate authenticity identification method and the system are compatible with authenticity identification of the identity card and the passport, have strong anti-interference capability, can meet the requirements of collection and authenticity identification of various situations, and have wide universality and applicability; and multiple safety protection false identification is provided, the false identification accuracy can be improved under the condition of ensuring the efficiency, and the requirement of the certificate identification and reading false identification technical field is met.
Description
Technical Field
The invention belongs to the technical field of license identification and counterfeit identification, and particularly relates to a license identification method and system based on a CIS image acquisition system.
Background
A passport is a legal document issued by a country to certify the nationality and identity of a citizen when the citizen of the country moves into and out of the country's border and travels to a foreign country or resides. Passports are necessary certificates for people, whether in airports or customs. The identity card is the most important identity card for everyone in China, and can be used when people take trains, send express or sit on airplanes. Therefore, the identification and the counterfeit identification of the certificate are very important.
The existing identification card detection technology, such as the second generation identification card authenticity identification method and device disclosed in the Chinese patent with the application number of 201310355211.2, compares the character information and the face image stored in the chip built in the identification card with the character information and the face image on the surface of the identification card respectively, and judges the authenticity of the identification card by the difference value of the similarity and the preset threshold value; the authenticity of the identity card can be identified without being limited by an identity card data database, so that the authenticity identification efficiency of the second-generation identity card is improved; however, with the appearance of more and more counterfeit certificates, the definition of images collected by the existing certificate reader cannot meet the current counterfeit identification requirement, and great potential safety hazards are brought along therewith. In the prior art, a CIS tube is adopted for bill collection, and the collection of bill images is completed by a transmission device from one end of equipment to the other end; however, the number of sheets of the passport exceeds one page, and the passport with the number of pages exceeding one page and needing to be turned cannot be subjected to image acquisition from one end of the equipment to the other end through the transmission device, so that the passport is not suitable for certificate authentication.
Disclosure of Invention
Aiming at the defects or improvement requirements of the prior art, the invention provides a certificate authenticity identification method and system based on a CIS image acquisition system, and aims to improve the authenticity identification accuracy rate under the condition of ensuring the efficiency.
In order to achieve the above object, according to an aspect of the present invention, there is provided a certificate authentication method based on a CIS image capturing system, including the steps of:
(1) respectively obtaining white light images, infrared images and ultraviolet images of the license under the white light images, the infrared images and the ultraviolet images; white light, infrared light and ultraviolet light respectively correspond to different anti-counterfeiting characteristics;
(2) correcting the license image;
(3) detecting and dividing a reading area of the certificate;
(4) identifying surface characters of the license image;
(5) and reading the chip information and performing authentication and counterfeit identification.
Preferably, the authentication method includes the following steps in step (2):
(2.1) carrying out color correction and white balance treatment on the white light, infrared and ultraviolet images of the license;
(2.2) searching and searching four boundaries of the license image on the gray level image of the processed infrared image;
(2.3) performing correction processing on the four boundaries;
(2.4) calculating intersection points between every two of the four boundaries, namely four corner points of the license edge, according to the corrected four boundaries;
and (2.5) respectively carrying out perspective transformation on the white light, infrared and ultraviolet images of the license by using the computed four corner points and a perspective transformation matrix computed by the calibration value computed by the improved multidirectional calibration algorithm to obtain the corrected white light, infrared and ultraviolet images.
Preferably, the authentication method includes the following steps in step (3):
(3.1) carrying out gray processing on the corrected infrared image;
(3.2) detecting a face position area on the grayed infrared image and extracting a face image;
(3.3) detecting a character position area on the grayed infrared image;
and (3.4) detecting a single character in each character position area.
Preferably, the authentication method includes the following steps in step (4):
(4.1) judging whether the infrared image is an identity card or a passport according to the surface characteristics of the infrared image after the license correction;
(4.2) extracting different features aiming at characters in different areas of the corrected infrared image;
(4.3) carrying out prediction and recognition on characters in different areas and a correspondingly trained sample library through an SVM classifier; and (4.4) summarizing the recognition result and outputting the recognition result to a graphical interface.
Preferably, the authentication method includes the following steps in step (5):
and (5.1) reading the license chip information through a chip reading device.
And (5.2) carrying out information comparison by using the surface image character recognition result and the chip self character information.
And (5.3) comparing the picture with the field collected image by utilizing the surface face image and the chip image.
And (5.4) comprehensively carrying out anti-counterfeiting characteristic identification on the image by using texture characteristic detection.
Preferably, the above mentioned authentication method further comprises the following sub-step (5)
(5.5) if the passport image is collected, the identity card can be placed in the upper sensing area, one-dimensional enhancement comparison is added, and the character and image information in the identity card chip is added to the compared information.
According to another aspect of the present invention, there is provided a certificate authenticity identification system based on a CIS image acquisition system, comprising a transmission device, a CIS tube image acquisition system, a main control module, an identification card or passport chip reading module, an upper computer interface, and a computer program stored in the upper computer and executing the steps of the certificate authenticity identification method when called;
the CIS tube image acquisition system is used for acquiring infrared, white light and ultraviolet images of the license; the conveying device is used for moving the CIS pipe image acquisition system to acquire images at different positions; the main control module is used for communicating with an external upper computer to control the acquisition of the CIS tube image acquisition system; the identity card or passport chip reading module is used for reading information stored in the identity card or passport chip; and the upper computer interface is used for sending the acquired image data packet and the acquired instruction to an external upper computer and sending the image acquisition instruction sent by the upper computer to the CIS pipe image acquisition system.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
(1) according to the certificate authenticity identification method and system based on the CIS image acquisition system, the CIS image acquisition system is used for image acquisition, the CIS tube of the CIS image acquisition system acquires uniform illumination and higher imaging quality than acquisition equipment such as a camera, a video camera and the like, and a reflection phenomenon possibly caused by a camera light source does not exist, so that the imaging quality, the image acquisition rate and the real-time performance are improved;
(2) the license authentication method and system based on the CIS image acquisition system are compatible with the authentication of the identity card and the passport, have strong anti-interference capability, can meet the acquisition and authentication requirements of various situations (the identity card, the passport and the identity card can be simultaneously used), and have wide universality and applicability;
(3) the license authentication method based on the CIS image acquisition system provided by the invention calibrates the face acquired on site, the face inside the chip and the face picture on the surface of the chip, synthesizes the characters on the surface of the license, the characters stored in the license chip and the anti-counterfeiting characteristics on the surface of the license to form multiple safety protection authentication, thereby improving the accuracy of the authentication and meeting the requirements of the technical field of license identification and reading the authentication under the condition of ensuring the efficiency.
Drawings
FIG. 1 is a schematic structural diagram of an embodiment of a certificate authentication system based on a CIS image acquisition system according to the present invention;
FIG. 2 is a schematic diagram of an external structure of a certificate authentication system based on a CIS image acquisition system according to an embodiment;
FIG. 3 is a schematic flowchart of an embodiment of a certificate authentication method based on a CIS image acquisition system according to the present invention;
FIG. 4 is a schematic diagram of a correction flow of a certificate authentication method based on a CIS image acquisition system according to an embodiment;
FIG. 5 is a schematic flowchart of a method for detecting and segmenting a reading region according to an authentication and counterfeit identification method of a CIS image acquisition system provided by the embodiment;
FIG. 6 is a schematic flowchart of surface character recognition based on a certificate authentication method of a CIS image acquisition system according to an embodiment;
fig. 7 is a schematic view of a certificate image identification flow of the certificate image identification method based on the CIS image acquisition system according to the embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Referring to fig. 1 and fig. 2, the present invention provides a schematic diagram of an embodiment of a certificate authentication system based on a CIS image acquisition system; the identification card or passport chip identification method specifically comprises a transmission device, a CIS tube image acquisition system, a main control module, an identity card or passport chip reading module, an upper computer interface and a computer program which is stored in the upper computer and executes the steps of the identification card or passport chip identification method when the identification card or passport chip reading module is called;
the CIS tube image acquisition system is used for acquiring infrared, white light and ultraviolet images of the license; the conveying device is used for moving the CIS pipe image acquisition system to acquire images at different positions; the main control module is used for communicating with an external upper computer to control the acquisition of the CIS tube image acquisition system; the identity card or passport chip reading module is used for reading information stored in the identity card or passport chip; and the upper computer interface is used for sending the acquired image data packet and the acquired instruction to an external upper computer and sending the image acquisition instruction sent by the upper computer to the CIS pipe image acquisition system.
When a passport or an identity card to be identified is placed into the license identification system, an entering signal of the license is obtained by three induction modes of real-time insertion of infrared induction, illumination change induction (from bright to dark) and mechanical transmission induction of a placement area built by rising and falling of a light barrier; the CIS tube image acquisition system receives the entering signal, synchronously acquires white light, ultraviolet and infrared images through the transmission device, packs the acquired image data through the upper computer interface and then transmits the packed image data to the upper computer for image splicing. The certificate authentication system based on the CIS image acquisition system provided by the embodiment overcomes the defect that the image acquisition of a plurality of sheets of certificates with the number of pages exceeding 1 page cannot be realized by the conventional CIS tube image acquisition device in a mode of fixing the CIS tube by transmitting the certificates.
In the embodiment, the upper computer interface adopts a USB interface, and the upper computer adopts a computer; the computer is used for carrying out preliminary detection on the image content, carrying out boundary pre-detection after processing the image through a susan operator, judging whether the acquired image belongs to an effective image or not by extracting a characteristic value through sampling projection, and carrying out license authentication according to the effective image.
In the embodiment, the certificate authentication method based on the CIS image acquisition system has the flow as shown in FIG. 3, and includes the steps of correcting a certificate image, detecting and dividing a certificate image recognition area, recognizing surface characters of the certificate image, reading information of a certificate chip and authenticating the certificate image.
The process of correcting the license image is shown in fig. 4, and comprises the following steps:
(2.1) performing color correction and white balance treatment on the white light, infrared and ultraviolet images of the license;
in the embodiment, an image correction algorithm based on the combination of point-by-point compensation and white balance is used for color correction, and the following is specifically used:
(2.1.1) establishing a photosensitive curve model function gi(I)＝kiI+bi；
Wherein, gi(I) The gray value output by the sensor I is shown, and the I is the illumination intensity; k is a radical ofiRepresenting the light sensitivity of the ith sensor, biThe initial gray scale of the ith sensor;
in order to eliminate the noise existing in the image itself, the photosensitive characteristic is corrected,
(2.1.2) setting Gi(I) For the corrected i-th sensor output gray value, ki' iskiCompensation value of biIs' aiA compensation value of (1), then Gi(I)＝(ki+ki')I+(bi+bi')；
In an embodiment, the CIS image capturing system uses 8-bit gray scale, the gray scale value ranges from 0 to 255, theoretically, the gray scale value of the black area of the correction paper is 0, the gray scale value of the white area is 255, and the sum of (g)bi，0)，(gwi255) these two sets of values are substituted in to obtain the corresponding correction coefficients.
(2.13) for the acquired image itself, assume R, G, B that the average of the three components tends to the same gray level K; let K be (R1+ G1+ B1)/3, where R1, G1, and B1 respectively represent the average values of three channels, red, green, and blue;
(2.1.4) calculating the gain of each channel respectively: K/R1; Kg-K/G1; kb is K/B1; taking gains Kr, Kg and Kb of each channel as product terms for correction, and multiplying the pixels of different channels by related coefficients;
(2.1.5) correcting related errors caused by a collecting tube of the CIS image collecting system through black and white paper;
through point-by-point compensation correction and white balance processing on the image, noise can be effectively filtered, and the image quality is improved.
(2.2) searching four boundaries of an upper boundary, a lower boundary, a left boundary and a right boundary on the gray-scale image of the license infrared image; and correction processing is performed on the four boundaries.
The method specifically comprises the following substeps:
(2.2.1) carrying out susan operator edge detection processing on the infrared image;
(2.2.2) searching four boundaries, namely an upper boundary, a lower boundary, a left boundary and a right boundary on the edge detection graph of the infrared image by adopting a step progressive backtracking method;
when the corresponding target point is not searched, detecting by adopting a large step length until the target point appears, searching forwards after reaching the first target point, and progressively searching by adopting a medium step length to further eliminate noise interference; the backward search adopts small-step backtracking search, and when a critical point is reached, pixel-by-pixel search and medium-step progressive search confirmation are carried out before and after the critical point; searching an upper boundary of a license image, starting searching from the upper boundary of the image, adopting a large-step downward search until the gray value of a certain pixel point is found to be smaller than a set threshold, then using a middle step downward to continue to search for N times in a progressive manner, wherein N is 3 in the embodiment; and if the subsequent values are all smaller than the set threshold value, judging that the upper boundary is close to the first target point, adopting small-step backtracking search until a point smaller than the threshold value and a point larger than the threshold value appear in succession, and adopting pixel-by-pixel search to confirm the range.
If the search for the boundary near the first target point fails, the boundary characteristics are not met, possibly caused by noise, the second target point is searched, and the same strategy is adopted until the corresponding upper boundary point is found. If the search is not found after exceeding a certain area, adopting middle step backtracking search to prevent the condition of missing the upper boundary point, and then carrying out transverse search to obtain a series of upper boundary points.
Then calculating the gradient of each upper boundary point, sequencing all the boundary points obtained by searching according to the gradient size, calculating the median of the gradient, and removing the invalid or wrong upper boundary points by using a K-means clustering algorithm to obtain the valid upper boundary points; and performing least square method fitting straight line on the effective upper boundary point, wherein the obtained straight line is the upper boundary.
And respectively obtaining a lower boundary, a left boundary and a right boundary by adopting the same method.
(2.3) correcting the four boundaries by a hough transform;
(2.4) calculating intersection points between every two of the four boundaries, namely four corner points of the license edge;
when there are any two straight lines y ═ k1x+b1And y ═ k2x+b2When and k is1≠0∪k2Not equal to 0, the coordinates of the intersection point of the two straight lines are
And sequentially solving the four obtained boundaries pairwise to obtain four angular points.
And (2.5) respectively carrying out perspective transformation on the white light, infrared and ultraviolet images of the license by using the computed four corner points and a perspective transformation matrix computed by the calibration value computed by the improved multidirectional calibration algorithm to obtain the white light, infrared and ultraviolet images corrected by the license.
In the embodiment, the method comprises the steps of calibrating by using black and white staggered checkered paper, putting the checkered paper into a collector to collect an image, and carrying out multi-directional detection on black and white critical points in the image; taking pixel points in eight directions (15 degrees, 60 degrees, 105 degrees, 150 degrees, 195 degrees, 240 degrees, 285 degrees and 330 degrees in the embodiment) of a target point as characteristic points, calculating an internal reference matrix and an external reference matrix according to vector information of the characteristic points, further solving a distortion coefficient by adopting a steepest descent algorithm, and storing the distortion coefficient into the matrix to form a calibration coefficient;
and carrying out perspective transformation on the acquired infrared, white light and ultraviolet images by adopting a calibration coefficient to obtain corrected images, cutting out a target area of the corrected images according to the corrected boundary information and the information of the angular points, and removing a background part.
The detection and segmentation process of the license image recognition area is shown in fig. 5, and comprises the following steps:
(3.1) carrying out gray processing on the infrared image subjected to the certificate correction;
in the embodiment, the OTSU algorithm is adopted to perform graying processing on the infrared image, and the image is processed by determining the optimal segmentation threshold of the foreground and the background.
(3.2) detecting a face position area on the gray level image obtained in the step (3.1) and extracting a face image;
carrying out graying processing on the characters of the passport and the identity card and the face area by an OTSU algorithm, and then carrying out edge detection by adopting a susan operator; detecting connected domains of characters of the license and the face region, after determining the approximate region, respectively diffusing the characters to the periphery on the gray level image to detect pixel by pixel, and judging the region edge; by searching and confirming the upper edge point, the lower edge point, the left edge point and the right edge point, the vertical boundary line and the horizontal boundary line are fitted, and the cutting is kept and is used for identifying the false.
(3.3) detecting a character position area on the gray level image obtained in the step (3.1);
performing edge detection on the character area of the license by adopting a susan operator, and covering the extracted face area by using black pixels; and then combining a connected domain detection and projection method, and filtering an invalid region and a region for fixing the character position according to the size and the position characteristics of the region.
And (3.4) detecting and dividing the single character in the character position area.
The method comprises the steps of carrying out secondary processing on the conditions of Chinese character adhesion, left-right structures, left-middle-right structures and the like aiming at the areas with Chinese characters, and specifically carrying out comprehensive judgment through setting of a plurality of thresholds, aspect ratio constraint, connected domain analysis and pre-recognition.
The process of recognizing the surface characters of the license image is shown in fig. 6, and comprises the following steps:
and (4.1) reading the infrared image after the license correction, and judging the type of the license.
If the face image on the infrared image is on the upper left side, the text area on the right side of the face image is about six lines and two columns, and two lines of machine-readable codes are arranged on the lower side, the certificate type is judged to be a passport;
if the face image on the infrared image is on the upper right and a line of numbers is arranged below the face image, judging that the certificate type is an identity card;
and (4.2) extracting different features aiming at the characters of different areas.
In the embodiment, all the regions are classified into the following first to sixth types: a numeric area, an English character area, a numeric character fusion area, a Chinese character gender area, a Chinese character ethnic area and a Chinese character overall area; and respectively marking the first type area to the sixth type area, and extracting different characteristics from different areas. And extracting partial HOG features and improved HAAR features from the first, second and third types of regions, wherein the fourth type of region uses partial HOG features, and the fifth and sixth types of regions use improved coarse peripheral features, coarse grid features and partial HOG features to perform multi-feature fusion feature extraction.
And (4.3) carrying out prediction recognition on the characters in different areas and the corresponding trained sample base through an SVM classifier.
The sample library also corresponds to six types of areas, the characteristics of corresponding different areas are used for extraction when the samples are trained, and the extracted characteristics are input into an SVM classifier for training and corresponding training results are output; and after the characteristics of the segmented characters are extracted, inputting the characters into a sample library of a corresponding region for prediction and identification according to the region division, and outputting the result.
And (4.4) summarizing the recognition results and outputting the recognition results to a graphical interface.
Specifically, the recognition results of the single characters are combined according to the actual row and column positions of the characters, integrated into specific information and output to the graphical interface.
The information reading and authentication flow of the license chip and the authentication image is shown in fig. 7, and comprises the following sub-steps:
and (5.1) reading the license chip information through a chip reading device.
Using the judgment result of the certificate to call different chip reading equipment to read corresponding information, transmitting and decoding the information, storing character information and pictures stored in the chip and displaying the character information and the pictures in a computer graphic interface;
and (5.2) performing information comparison by using the surface image character recognition result and the chip storage character information.
Specifically, aiming at the identity card, six items of information, namely name, gender, ethnic group, birthday, address and identity card number, are compared and checked;
aiming at the passport, the nationality, the type, the passport number, the surname, the first name, the gender, the birth place, the birth date, the issuing place, the issuing date, the validity period, the issuing organization and the machine-readable code are compared and checked.
And (5.3) comparing the picture with the field collected image by utilizing the surface face image and the chip image.
Firstly, carrying out face verification on a face image on the surface of a certificate and an image stored in a chip; and then carrying out secondary face verification on the face image acquired on site and the image stored in the chip, and outputting a verification result.
(5.4) the anti-counterfeiting characteristic identification is carried out on the information of the image by using texture characteristic detection, and the method specifically comprises the following substeps:
(5.4.1) determining anti-counterfeiting point information needing to be verified of the image per se according to the nationality information and the license type information, wherein the anti-counterfeiting point information comprises white-light image anti-counterfeiting points, infrared image anti-counterfeiting points, ultraviolet image anti-counterfeiting points and white-light infrared ultraviolet crossed anti-counterfeiting point information;
(5.4.2) directionally retrieving according to the specific anti-counterfeiting points, and matching the information of the corresponding anti-counterfeiting points by adopting a sliding window detection method to check whether the number of the pixel points in the target area reaches the standard or not;
and (5.4.3) comprehensively identifying and judging the authenticity of the image according to the anti-counterfeiting characteristics of the characters, the human face and the image.
After the step (5.4), preferably, a step (5.5) of enhancing verification is further included, the passport is authenticated, if the passport and the identity card are required to be verified at the same time, the information stored in the identity card chip is compared with the name, the sex and the date of birth in the passport, and then the image in the identity card chip and the image in the passport chip are subjected to face verification for three times, so that the accuracy of the authentication is improved.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (5)
1. A certificate authentication method based on a CIS image acquisition system is characterized by comprising the following steps:
(1) acquiring white light images, infrared images and ultraviolet images of the license under the white light, infrared images and ultraviolet images, wherein the acquisition of the images at different positions is completed by moving a CIS tube image acquisition system, specifically, the CIS tube image acquisition system receives an incoming signal, synchronously acquires the white light images, the ultraviolet images and the infrared images through a transmission device, packs the acquired image data through an upper computer interface and then transmits the packed image data to an upper computer for image splicing;
(2) correcting the white light, infrared and ultraviolet images of the license;
(3) detecting and dividing a reading area of the certificate;
(4) identifying surface characters of the license image;
(5) reading chip information and performing certificate authentication;
wherein, the step (2) comprises the following substeps:
(2.1) carrying out color correction and white balance treatment on the white light, infrared and ultraviolet images of the license;
(2.2) searching and searching four boundaries of the license image on the gray level image of the processed infrared image;
(2.3) performing correction processing on the four boundaries;
(2.4) calculating intersection points between every two of the four boundaries, namely four corner points of the license edge, according to the corrected four boundaries;
(2.5) respectively carrying out perspective transformation on the white light, the infrared and the ultraviolet images of the license by using the computed four angular points and a perspective transformation matrix computed by the calibration value computed by the improved multidirectional calibration algorithm to obtain the corrected white light, infrared and ultraviolet images;
specifically, the method comprises the steps of calibrating by using black and white staggered checkered paper, putting the checkered paper into a collector to collect an image, and carrying out multi-directional detection on black and white critical points in the image; taking pixel points of the target point in eight directions as characteristic points, calculating an internal reference matrix and an external reference matrix according to vector information of the characteristic points, further solving a distortion coefficient by adopting a steepest descent algorithm, and storing the distortion coefficient in the matrix to form a calibration coefficient, wherein the eight directions are 15 degrees, 60 degrees, 105 degrees, 150 degrees, 195 degrees, 240 degrees, 285 degrees and 330 degrees; carrying out perspective transformation on the collected infrared, white light and ultraviolet images by adopting a calibration coefficient to obtain corrected images, cutting out a target area of the corrected images according to the corrected boundary information and the information of angular points, and removing a background part;
wherein, the step (2.2) comprises the following substeps:
(2.2.1) carrying out susan operator edge detection processing on the infrared image;
(2.2.2) searching four boundaries, namely an upper boundary, a lower boundary, a left boundary and a right boundary on the edge detection graph of the infrared image by adopting a step progressive backtracking method;
wherein, the step (4) comprises the following substeps:
(4.1) judging whether the infrared image is an identity card or a passport according to the surface characteristics of the infrared image after the license correction;
(4.2) extracting different features aiming at characters in different areas of the corrected infrared image;
(4.3) carrying out prediction and recognition on characters in different areas and a correspondingly trained sample library through an SVM classifier;
(4.4) summarizing the recognition results and outputting the recognition results to a graphical interface;
wherein, the step (5) comprises the following substeps:
(5.1) reading the information of the license chip through a chip reading device;
(5.2) carrying out information comparison by using the surface image character recognition result and the character information of the chip;
(5.3) comparing the surface face image and the chip image with the field collected image;
and (5.4) comprehensively carrying out anti-counterfeiting characteristic identification on the image by using texture characteristic detection.
2. A license authentication method according to claim 1, wherein the step (2.1) comprises the substeps of:
(2.1.1) establishing a photosensitive curve model function gi(I)＝kiI+bi；
Wherein, gi(I) The gray value output by the sensor I is shown, and the I is the illumination intensity; k is a radical ofiRepresenting the light sensitivity of the ith sensor, biThe initial gray scale of the ith sensor;
(2.1.2) setting Gi(I) For the corrected i-th sensor output gray value, kiIs' kiCompensation value of biIs' aiA compensation value of (1), then Gi(I)＝(ki+ki')I+(bi+bi')；
(2.13) for the acquired image itself, assume R, G, B that the average of the three components tends to the same gray level K; let K be (R1+ G1+ B1)/3, where R1, G1, and B1 respectively represent the average values of three channels, red, green, and blue;
(2.1.4) calculating the gain of each channel respectively: K/R1; Kg-K/G1; kb is K/B1; taking the gains Kr, Kg and Kb of each channel as product terms for correction, and multiplying the pixels of different channels by related coefficients;
and (2.1.5) correcting related errors caused by an acquisition tube of the CIS image acquisition system through black and white paper.
3. The license authentication method as claimed in claim 1, wherein the step (3) comprises the substeps of:
(3.1) carrying out gray processing on the corrected infrared image;
(3.2) detecting a face position area on the grayed infrared image and extracting a face image;
(3.3) detecting a character position area on the grayed infrared image;
and (3.4) detecting a single character in each character position area.
4. The license authentication method according to claim 1, wherein the step (5) further comprises the substeps of,
(5.5) if the passport image is collected, placing the identity card in an upper sensing area, adding one-dimensional enhancement comparison, and adding character and image information in an identity card chip to the compared information.
5. A license authentication system based on the license authentication method of any one of claims 1 to 4, comprising a transmission device, a CIS tube image acquisition system, a main control module, an identity card or passport chip reading module, an upper computer interface, and a computer program which is stored in the upper computer and executes the steps of the license authentication method of any one of claims 1 to 4 when being called;
the CIS tube image acquisition system is used for acquiring infrared, white light and ultraviolet images of the license; the conveying device is used for moving the CIS pipe image acquisition system to acquire images at different positions; the main control module is used for communicating with an external upper computer to control the acquisition of the CIS tube image acquisition system; the identity card or passport chip reading module is used for reading information stored in the identity card or passport chip; and the upper computer interface is used for sending the acquired image data packet and the acquired instruction to an external upper computer and sending the image acquisition instruction sent by the upper computer to the CIS pipe image acquisition system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810190966.4A CN108563990B (en) | 2018-03-08 | 2018-03-08 | Certificate authentication method and system based on CIS image acquisition system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810190966.4A CN108563990B (en) | 2018-03-08 | 2018-03-08 | Certificate authentication method and system based on CIS image acquisition system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108563990A CN108563990A (en) | 2018-09-21 |
| CN108563990B true CN108563990B (en) | 2022-03-29 |
Family
ID=63532534
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810190966.4A Active CN108563990B (en) | 2018-03-08 | 2018-03-08 | Certificate authentication method and system based on CIS image acquisition system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108563990B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920990A (en) * | 2018-09-28 | 2018-11-30 | 五邑大学 | A kind of identity card identification Verification System |
| CN109740586B (en) * | 2018-12-19 | 2022-08-16 | 南京华科和鼎信息科技有限公司 | Automatic reading system and method for anti-dazzle certificate |
| CN112560850A (en) * | 2019-09-26 | 2021-03-26 | 中电万维信息技术有限责任公司 | Automatic identity card information extraction and authenticity verification method based on custom template |
| CN110765884B (en) * | 2019-09-29 | 2022-07-26 | 华中科技大学 | Multi-type certificate card authenticity identification method and equipment |
| CN110929725B (en) * | 2019-12-06 | 2023-08-29 | 深圳市碧海扬帆科技有限公司 | Certificate classification method, device and computer readable storage medium |
| CN111582259B (en) * | 2020-04-10 | 2024-04-16 | 支付宝实验室(新加坡)有限公司 | Machine-readable code identification method, device, electronic equipment and storage medium |
| CN111738979B (en) * | 2020-04-29 | 2024-01-19 | 北京易道博识科技有限公司 | Certificate image quality automatic checking method and system |
| CN111860486B (en) * | 2020-07-27 | 2023-10-31 | 平安科技（深圳）有限公司 | Card identification method, device and equipment |
| CN112381080B (en) * | 2020-11-06 | 2022-08-16 | 长城信息股份有限公司 | Certificate reading method, device, equipment and medium supporting multi-protocol type |
| CN113449686A (en) * | 2021-07-19 | 2021-09-28 | 成都新希望金融信息有限公司 | Identification method, device, equipment and medium for identity card counterfeiting |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006085265A (en) * | 2004-09-14 | 2006-03-30 | Fuji Photo Film Co Ltd | Identification device, method and program |
| CN101751785A (en) * | 2010-01-12 | 2010-06-23 | 杭州电子科技大学 | Automatic license plate recognition method based on image processing |
| CN103426016A (en) * | 2013-08-14 | 2013-12-04 | 湖北微模式科技发展有限公司 | Method and device for authenticating second-generation identity card |
| CN105528601A (en) * | 2016-02-25 | 2016-04-27 | 华中科技大学 | Identity card image acquisition and recognition system as well as acquisition and recognition method based on contact type sensor |
| CN105866051A (en) * | 2016-03-26 | 2016-08-17 | 南京华科和鼎信息科技有限公司 | Portable card and passport check meter and use method thereof |
| CN106650560A (en) * | 2015-11-04 | 2017-05-10 | 上海市公安局刑事侦查总队 | Identity authentication method based on identity card and identity authentication processor and system thereof |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101876532B (en) * | 2010-05-25 | 2012-05-23 | 大连理工大学 | Camera on-field calibration method in measuring system |
| CN102789642B (en) * | 2011-05-16 | 2017-08-25 | 索尼公司 | Direction of extinction determines method and apparatus, camera self-calibration method and device |
| CN104574401A (en) * | 2015-01-09 | 2015-04-29 | 北京环境特性研究所 | Image registration method based on parallel line matching |
-
2018
- 2018-03-08 CN CN201810190966.4A patent/CN108563990B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006085265A (en) * | 2004-09-14 | 2006-03-30 | Fuji Photo Film Co Ltd | Identification device, method and program |
| CN101751785A (en) * | 2010-01-12 | 2010-06-23 | 杭州电子科技大学 | Automatic license plate recognition method based on image processing |
| CN103426016A (en) * | 2013-08-14 | 2013-12-04 | 湖北微模式科技发展有限公司 | Method and device for authenticating second-generation identity card |
| CN106650560A (en) * | 2015-11-04 | 2017-05-10 | 上海市公安局刑事侦查总队 | Identity authentication method based on identity card and identity authentication processor and system thereof |
| CN105528601A (en) * | 2016-02-25 | 2016-04-27 | 华中科技大学 | Identity card image acquisition and recognition system as well as acquisition and recognition method based on contact type sensor |
| CN105866051A (en) * | 2016-03-26 | 2016-08-17 | 南京华科和鼎信息科技有限公司 | Portable card and passport check meter and use method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 基于多光谱图像的澳元防伪鉴定研究;李山雨;《中国优秀硕士学位论文全文数据库 信息科技辑》;20161215(第12期);I138-309页正文第2章，第4章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108563990A (en) | 2018-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108563990B (en) | Certificate authentication method and system based on CIS image acquisition system | |
| CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
| US20170220886A1 (en) | Method and system for reading and validating identity documents | |
| CN105956578B (en) | A kind of face verification method of identity-based certificate information | |
| CN111401372B (en) | Method for extracting and identifying image-text information of scanned document | |
| CN109684987B (en) | Identity verification system and method based on certificate | |
| CN108009531B (en) | Multi-strategy anti-fraud face recognition method | |
| US9760788B2 (en) | Mobile document detection and orientation based on reference object characteristics | |
| CN107491730A (en) | A kind of laboratory test report recognition methods based on image procossing | |
| CN106529414A (en) | Method for realizing result authentication through image comparison | |
| CN110008909B (en) | Real-name system business real-time auditing system based on AI | |
| CN112818722B (en) | Modular dynamic configurable living body face recognition system | |
| CN111462379A (en) | Access control management method, system and medium containing palm vein and face recognition | |
| CN106650623A (en) | Face detection-based method for verifying personnel and identity document for exit and entry | |
| CN107195069A (en) | A kind of RMB crown word number automatic identifying method | |
| CN109102003A (en) | A kind of small target detecting method and system based on Infrared Physics Fusion Features | |
| CN106991448A (en) | A kind of portrait compares processing method | |
| CN113642639A (en) | Living body detection method, living body detection device, living body detection apparatus, and storage medium | |
| CN114842524B (en) | Face false distinguishing method based on irregular significant pixel cluster | |
| CN108021913A (en) | Certificate photograph information identifying method and device | |
| WO2018107574A1 (en) | Method and device for detecting see-through register anti-counterfeiting characteristics | |
| CN114445843A (en) | Card image character recognition method and device of fixed format | |
| KR101781351B1 (en) | Forgery passport inspection method and recording medium thereof | |
| CN110991434B (en) | Self-service terminal certificate identification method and device | |
| CN112001318A (en) | Identity document information acquisition method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |